Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By telepenin
Route Claude's WebFetch calls through the agentify shared cache. First fetch extracts to clean markdown via Workers AI; every subsequent agent reading the same URL gets a cache hit and pays a fraction of the tokens.
npx claudepluginhub telepenin/aicorn --plugin aicornThis skill should be used when the user asks Claude to "fetch", "read", "scrape", "summarize", "extract", "open", or "what's on" a web URL — e.g. "fetch https://...", "read this article", "what does this page say". Routes the request through the agentify shared cache so the page is only extracted to markdown once across all agents, then served as a cheap cache hit.
Write a per-project configuration file at `.claude/aicorn.local.md` that the companion `fetch` skill reads to decide where and how to route `WebFetch` calls. The file uses YAML frontmatter for machine-readable values.
Crack the page once. Share the kernel.
Aicorn is a shared, credit-metered cache for agent-friendly web content. Built on Cloudflare Workers, Workers AI, and KV.
Every AI agent re-extracts the same HTML from the same websites and pays for the same LLM tokens to clean it up. Aicorn is the squirrel-network: one agent cracks the page, the kernel is stored, and every other agent harvests from the shared hoard. Contributors earn credits when their kernel is read.
Two agents, same URL, ten seconds apart.
Agent A → MISS → 8,000 tokens → $0.02 → contributor
Agent B → HIT → 400 tokens → $0 → reader pays 10, contributor earns 9
Same content. Same agent quality. 20× cheaper.
Cloudflare Workers · Workers AI · KV · TypeScript
Hackathon build, 5-hour scope. See TEAM.md for current ownership.
Share bugs, ideas, or general feedback.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Create and edit Obsidian vault files including Markdown, Bases, and Canvas. Use when working with .md, .base, or .canvas files in an Obsidian vault.
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). Proactively activates in projects with cacheComponents: true, providing patterns for 'use cache' directive, cacheLife(), cacheTag(), cache invalidation, and parameter permutation rendering.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions
Configure Claude Code telemetry for Claudicle
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim